The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes content from the project's codebase and wiki surfaces.\n
Ingestion points: Reads projects/<project>/architecture/domain-language.md, projects/<project>/decisions.md, CONTEXT.md, and arbitrary files during codebase exploration.\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands were identified in the ingestion logic.\n
Capability inventory: The skill can execute the wiki forge status command and perform file write operations to create or update documentation artifacts.\n
Sanitization: No sanitization or validation of the ingested external content is performed before processing.\n- [COMMAND_EXECUTION]: The skill includes instructions to invoke the wiki forge status command to verify the completion of the domain modeling phase. This is an intended operational component of the project workflow.\n- [NO_CODE]: The skill consists exclusively of markdown documentation and templates. It does not include any executable scripts, binaries, or external dependencies.

domain-model